Triple

T3965377
Position Surface form Disambiguated ID Type / Status
Subject Flesh and Stone E92204 entity
Predicate featuresSpecies P7733 FINISHED
Object Weeping Angel E15447 NE FINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Weeping Angel | Statement: [Flesh and Stone, featuresSpecies, Weeping Angel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Weeping Angel
Context triple: [Flesh and Stone, featuresSpecies, Weeping Angel]
  • A. Weeping Angels chosen
    The Weeping Angels are a terrifying race of predatory, statue-like creatures in Doctor Who that can only move when unobserved, sending victims back in time and feeding on the resulting temporal energy.
  • B. Wraith
    Wraith is a horror comic series by Joe Hill that expands on the sinister world and characters of his novel "NOS4A2."
  • C. Ghast
    A Ghast is a large, floating, ghost-like hostile mob in Minecraft’s Nether dimension that shoots explosive fireballs and emits eerie cries.
  • D. Angel of Death
    Angel of Death is a thriller novel by Jack Higgins that follows covert operatives confronting a deadly terrorist organization in modern-day Britain.
  • E. Lurch
    Lurch is the towering, gloomy butler of the eccentric Addams Family, known for his deep voice, slow movements, and deadpan demeanor.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69aed96624188190ac8c45bb57ab72b5 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aef97520588190922e56201fc3ca52 completed March 9, 2026, 4:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69b55619cb548190ac2553f23de9bfed completed March 14, 2026, 12:35 p.m.
Created at: March 9, 2026, 3:31 p.m.